Discriminatory power (Gini, AUC)

Roles that need it

• Credit Risk Model Developer
• Model Validation Analyst
• Data Scientist (Banking)

Skills it belongs to

• Credit risk models (IFRS 9, IRB)
• Machine learning fundamentals
• Hypothesis testing and significance

Related concepts

• Rating model (internal credit rating)A rating model assigns borrowers to grades on a scale that maps to a probability of default, using financial ratios, behavioural data and expert judgement. Retail versions are usually called scorecards. Ratings drive approval, pricing, limits, provisions and capital.
• BacktestingBacktesting compares a model's predictions with actual outcomes over time. For VaR it counts the days when losses exceeded the estimate; for credit models it compares predicted default rates with observed ones by grade. Too many exceptions signal a model that needs review.
• Model validationModel validation is the independent review that checks whether a model is conceptually sound, built on suitable data, correctly implemented and performing as intended for its use. It is done before first use and periodically after, and its findings feed model approval and the model risk framework.
• Probability of default (PD)Probability of default is the likelihood that a borrower defaults over a given horizon, usually one year. Capital models use a long-run average (through-the-cycle) PD per rating grade, while IFRS 9 uses point-in-time 12-month and lifetime PDs that react to the economic outlook.

Sources

• Guidelines on PD estimation, LGD estimation and treatment of defaulted assets, EBA (external site) accessed 31 Oct 2026

Updated 31 Oct 2026.